An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments.
Elaheh BaratiXuewen ChenPublished in: IJCAI (2019)
Keyphrases
- multi view
- actor critic
- reinforcement learning
- attention mechanism
- policy gradient
- temporal difference
- optimal control
- approximate dynamic programming
- reinforcement learning algorithms
- function approximation
- gradient method
- three dimensional
- d objects
- visual attention
- policy iteration
- model free
- state space
- optimal policy
- average reward
- learning algorithm
- semi supervised
- dynamic programming
- monte carlo
- rl algorithms
- viewpoint
- similarity measure
- machine learning
- transfer learning
- machine learning algorithms
- vision system
- optical flow
- reinforcement learning methods
- feature space